红外测温技术及在钢铁生产中的应用

红外测温技术的发展有助于对运动目标和微小目标实施快速准确无损的测温。通过对红外测温技术原理和系统的讨论,将测温方式分为点、线、面三种类型,比较分析了有代表性的红外测温仪器及特点;介绍了红外测温技术在现代钢铁生产的炼铁、炼钢、连铸、连轧等生产环节中的具体应用;指出了提高红外测温仪器抗干扰能力和精度,改善其系统设计,并将人工智能技术与红外测温技术相结合,加强温度信息处理和利用是未来红外技术发展的方向之一。     

MCFC热启动过程的人工神经网络建模分析

熔融碳酸盐燃料电池目前是燃料电池研究领域的一个难点，其严格的热启动过程对电池性能和寿命的影响至关重要。针对这一问题，建立了基于人工神经网络的熔融碳酸盐燃料电池热启动过程模型，详细给出了采用改进BP算法的熔融碳酸盐燃料电池热启动过程的模型结构、算法、训练和仿真。MATLAB仿真结果证明其快速准确，为熔融碳酸盐燃料电池热启动过程的控制提供了实际工程应用模型。     

基于BP人工神经网络的引水系统平硐围岩参数反演分析

鉴于影响围岩稳定性的一个重要因素是岩体的开挖、卸荷过程引起围岩质量劣化和变形,基于卸荷岩体力学理论及方法,利用BP人工神经网络对丹巴电站平硐围岩参数进行了反演,有效降低了参数选取过程中的主观因素,并将反演所得参数代入三维模型进行数值模拟计算。结果表明,计算所得的测线收敛值变化趋势与监测数据大致相同,可见利用BP人工神经网络能获得反映岩体真实性能的参数值。     

BP人工神经网络模型在溪洛渡、向家坝两库联合优化调度规则中的应用

基于BP人工神经网络算法的基本原理,采用水库水位与出力双决策控制,建立了溪洛渡、向家坝两库联合调度函数的BP人工神经网络模型。模拟调度结果表明,该模型能更好地映射调度函数中各变量之间的非线性关系,优化运行轨迹的拟合效果明显提高。     

BP神经网络在水轮机调节过程中的应用

由于水轮机调节系统的大惯性、"水锤"效应等特点及其结构复杂等问题,采用传统的常规PID控制已很难满足控制要求,控制品质也难以改善,控制过程中易发生超调量大、震荡频次多、收敛时间过长等问题。对此,在常规PID控制基础上设计了基于BP神经网络自适应PID控制,并在Matlab软件中完成相关程序的编写及仿真试验。仿真结果表明,基于BP神经网络自适应PID控制是一种有效的水轮机调速器参数整定方法,相较于常规PID控制能获得更好的动态性能。     

石油化工生产过程节能实例的综合分析

<正> 石化企业的节能主要包括两个方面,一是充分利用余热、余能,二是尽量减少工艺过程本身的能耗。七十年代以来,由于广泛采用了催化技术、废热回收技术、燃烧技术、计算机控制技术及高效节能设备等,使得生产能耗有了大幅度的降低。笔者在多年的效益审计和建设项目的审计工作中,涉及了大量的节能工作,本     

BP网络在汽轮机调节系统参数估计中的应用研究

将ＢＰ网络应用于汽轮机调节系统的参数辨识，训练与测试结果表明，ＢＰ网络在系统参数评估时具有较高的可靠性和估计精度，误差在５％以内的置信度达９０％以上。     

基于主成分分析和BP神经网络的赣江流域中长期径流预报

针对赣江流域开展水量调度对中长期径流预报的迫切需求,在分析赣江流域径流特性的基础上,以降雨、径流等常规因子和130项大气环流指数等相关因子为预报因子,分别构建基于相关系数法、逐步回归方法、主成分分析法三种因子筛选方法的BP神经网络中长期径流预报模型。研究结果表明,主成分分析方法筛选的预报因子可较好描述未来径流的变化趋势,所构建的基于主成分分析的BP神经网络中长期径流预报模型在率定期和检验期的合格率均满足规范对作业预报模型的精度要求,可作为赣江流域中长期径流预报的支撑模型。研究成果为赣江流域开展水资源优化配置和水量调度提供了依据。     

改进的BP神经网络在汽轮发电机组故障诊断中的应用

就BP网络的不足，提出了一种改进的BP神经网络模型，用于汽轮发电机组故障的诊断。经理论和实践证明：该方法有效地提高了故障诊断的精度和可靠度，为旋转机械故障诊断提供了有效方法。图2表4参7     

高密度沉淀池在钢铁废水处理中的应用

污水处理中心来水具有污染物种类多、成分复杂、难以处理等特点。通过总结某污水处理中心深度处理系统工程10个月的运行情况,摸索出了高密度沉淀池基本的运行参数。该工程10个月的运行表明,高密度沉淀池能有效去除浊度、COD和硬度,使出水浊度、COD和硬度达到设计目标,高密度沉淀池对NH3-N和铁除去效果不明显。     

应用人工神经网络处理HVAC非线性计算

介绍了将人工神经网络用于计算人体热感觉的PMV指标和绘制焓湿图。根据有关数据显示利用神经网络的计算值与实际值相吻合 ,说明神经网络是一种新颖、可靠的HVAC非线性计算方法。其结构在HVAC非线性实时控制中优势显著     

Exergy analysis of hydrogen-reduction based steel production with coal gasification-shaft furnace-electric furnace process

Carbon-free energy utilization in steel production is an effective way for China's iron and steel industry to achieve low carbon development. Thus, coal gasification-shaft furnace-electric furnace (CSE) technology, which use hydrogen-enriched gas for steel production, has recently become a sustainable topic of great concern. In the current study, the material flow analysis (MFA) and exergy assessment of the CSE process are conducted to investigate the material consumption and energy efficiency of this new steelmaking process. The exergy efficiency of the CSE process is calculated to be 50.11%, indicating a great potential for energy-saving. The results indicate that the coal gasification & gas purification that responsible for hydrogen-enriched gas production is the system with the largest exergy loss (account for 23.13% of the total exergy input), while the pelletizing system has the lowest efficiency (13.33%) due to heat loss. The key to further improve the thermal performance of this process lies in the heat recovery of the coal gasifier and pelletizing. It is also found that when the H₂ content in reducing gas rise from 57.00% to 100.00%, the exergy efficiency of the shaft furnace is only increased by 1.58%, while the demand volume of reducing gas significantly increases from 1326.30 Nm³/t to 2201.50 Nm³/t. The environmental benefits of hydrogen reduction based steelmaking must be considered together with energy utilization and production cost. The present work should do helpful effort for the application and further improvement of the CSE process in China.     

Electric load analysis using an artificial neural network

Load forecasting in the current, increasingly liberalized, electricity power market is of crucial importance as a means for producers to optimize and rationalize energy supply. A number of electric power companies are equipped to make forecasts with the aid of traditional statistical methods. This paper presents the use of an artificial neural net to an hourly based load forecasting application for a small electric grid on an Italian island (Lipari) not connected to the mainland. The aim was to examine the forecasting ability of a neural net in a situation where the electric load was subject to considerable seasonal variations over the year. The variations are affected by energy demand related to the tourism season as well as by climatic conditions, especially temperature. The network developed was a multi‐layer perceptron type built on three layers trained with a back‐propagation algorithm. The input layer receives all the most relevant information regarding: the class of day type, the hour in the daytime, the load and background temperature recorded at the indicated time for the months of March, August and October whilst the output layer provides the forecast value at the indicated time in December. The results obtained are encouraging; in the training phase the RMS error rate was around 2% and this rate settled at about 2.6% during testing. As both the margins of error recorded are acceptable, the use of a neural network for electric load forecasting applications can be considered an attractive option. Copyright © 2005 John Wiley & Sons, Ltd.     

A novel application of artificial neural network for wind speed estimation

Providing accurate multi-steps wind speed estimation models has increasing significance, because of the important technical and economic impacts of wind speed on power grid security and environment benefits. In this study, the combined strategies for wind speed forecasting are proposed based on an intelligent data processing system using artificial neural network (ANN). Generalized regression neural network and Elman neural network are employed to form two hybrid models. The approach employs one of ANN to model the samples achieving data denoising and assimilation and apply the other to predict wind speed using the pre-processed samples. The proposed method is demonstrated in terms of the predicting improvements of the hybrid models compared with single ANN and the typical forecasting method. To give sufficient cases for the study, four observation sites with monthly average wind speed of four given years in Western China were used to test the models. Multiple evaluation methods demonstrated that the proposed method provides a promising alternative technique in monthly average wind speed estimation.     

基于BP神经网络的球磨机磨矿浓度的预测分析

对球磨机磨矿过程的能耗进行分析,并利用灰色系统关联度分析法分析影响能耗因数,找出主要影响因数,通过BP神经网络建立球磨机磨矿浓度预测模型对磨矿浓度进行预测,对于降低球磨机能耗、解决冶金企业能耗问题具有一定的指导意义。     

应用神经网络方法预测生物质的热值

应用人工神经网络方法对生物质的热值进行了预测,网络的训练数据集来自美国Biomass Feedstock Composition and Property Database of U．S．Department of Energy。神经网络以生物质的工业分析结果作为输入数据．采用56组数据对网络进行训练,以7组数据对网络进行验证,对网络输出值与实际值进行比较,相对误差在0．08％以内。人工神经网络成功地预测各种生物质的热值,说明人工神经网络能够处理生物质的热值与工业分析各组分间的非线性关系。     

基于人工神经网络的供热管网终端温度预测模型

从供热管网终端泄漏诊断需要出发，引出求解正常供热时管网系统的终端温度。绕过传统的通过求解微分方程确定温度的方法，利用人工神经网络来预测管网系统的终端温度，从而为供热管网终端泄漏诊断提供参考依据。在应用人工神经网络时，采用基于相关分析法的节点删除法来优化网络结构提高网络性能。仿真分析表明基于这种结构优化的人工神经网络模型对供热管网终端温度预测较为准确，对泄漏诊断有一定帮助。     

基于BP神经网络的小型风力发电正弦波逆变器

为了提高小型风力发电系统的可靠性和能量转换效率,文章设计了一种带有高频环节的单相正弦逆变器,该逆变器提出采用双BP神经网络控制。在Matlab下建立了逆变器仿真模型,仿真结果表明,设计的BP神经网络控制器可以使单相正弦逆变器具有较高的稳态精度和动态特性,满足小型风力发电系统的需要。     

基于人工神经网络的机车当量模型的研究

研究了当前我国机车检修的现状,在传统的机务检修基础上建立了机车当量公里的模型,将机车运行过程中的公里量、负荷量和时间量通过人工神经网络训练进行学习,形成了一种确定机车检修周期的新方法,解决了确定我国铁路机车检修周期问题。     

基于BP神经网络的油冷器压降及换热量预测

油冷器作为发动机散热部件之一,压降和换热量是评估其性能的重要指标,但油冷器中传热与流动规律错综复杂,所以对其压降和换热量进行预测存在一定难度。本研究提出了一种基于BP神经网络和特征工程的预测方法。该方法通过实验获得不同结构类型下冷油器数据,对样本数据进行插值和增强等方法解决样本量分布不均的问题,并根据相关性计算Shah-Focke关联式、Gray and Web关联式、A.R.Wieting关联式等相关经验公式与本文实验结果相关性,并筛选出相关性最高的关联式来构造新特征,最后利用BP神经网络模型进行预测。结果表明,Shah-Focke关联式与本文实验结果相关性最高,且该经验公式特征的引入对模型有积极影响,预测精度提升50%,令压降预测误差为6%,换热量预测误差为4%。